Chinese Bedtime Story Generator

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:22 PM UTC
• Version: 1.0.1

Overview

This skill appears to do what it claims: generate Chinese bedtime stories and optional audio, while saving local story outputs and using external AI/TTS services.

Install only if you are comfortable sending the provided child profile details and generated story text to the configured LLM and TTS services. Prefer nicknames instead of real names, review provider privacy terms, and periodically delete the local outputs directory if using a shared or backed-up machine.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill documentation advertises use of environment variables, filesystem reads/writes, and network-backed LLM/TTS services, yet no explicit permissions are declared. This creates a transparency and governance gap: users or platforms cannot accurately assess what resources the skill will access before execution. In this context, the risk is elevated because the skill handles child-related personalization data and persists state across runs.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill writes persistent outputs including story text, audio files, and a state file containing child name, age, interests, and continuity data, but the user-facing description does not warn about this retention. Persistent storage of child-related data can lead to unintended disclosure on shared systems or later reuse beyond user expectations.

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The skill sends personalized child inputs and generated story content to external LLM and TTS services, but the description does not clearly warn users that this data may leave the local environment. Because the inputs include child-identifying and preference data, undisclosed third-party transmission creates a significant privacy risk and may conflict with user expectations or policy requirements.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill sends child name, age, interests, and generated story text to external LLM and TTS providers without any explicit consent flow, minimization, or privacy warning in the code path. Because this skill is specifically for children, transmitting child-related data to third-party services raises elevated privacy and compliance risk.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.30.0
requests>=2.31.0
python-dotenv>=1.0.0

• Confidence: 95% confidence
• Finding: The dependency is specified with a lower bound only, which allows future major or minor versions to be installed without review. This creates supply-chain and stability risk because a later release could introduce a security regression or breaking behavior that affects the skill.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.30.0
requests>=2.31.0
python-dotenv>=1.0.0

• Confidence: 98% confidence
• Finding: The requests dependency is unpinned, so installation may resolve to any newer version that satisfies the minimum bound, including versions with known advisories or future regressions. In a networked skill that likely calls external APIs, this increases exposure to transport-layer and credential-handling flaws in a core HTTP library.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.30.0
requests>=2.31.0
python-dotenv>=1.0.0

• Confidence: 93% confidence
• Finding: python-dotenv is also specified as a minimum version only, which permits uncontrolled upgrades at install time. While often lower risk than runtime network libraries, this still introduces supply-chain uncertainty and could expose the skill to vulnerable releases or unexpected behavior in environment file handling.

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High

• Category: Supply Chain
• Confidence: 94% confidence
• Finding: The file allows installation of requests versions associated with multiple published advisories, and the dependency is central to outbound HTTP communication. In this skill context, which likely interacts with remote APIs for LLM/TTS generation, a vulnerable HTTP client could leak credentials, mishandle TLS or redirects, or expose sensitive request data.

Known Vulnerable Dependency: python-dotenv — 1 advisory(ies): CVE-2026-28684 (python-dotenv: Symlink following in set_key allows arbitrary file overwrite via )

Low

• Category: Supply Chain
• Confidence: 79% confidence
• Finding: The dependency is flagged for a symlink-following issue in set_key, which can enable arbitrary file overwrite if the vulnerable API is used on attacker-controlled paths. In this skill's apparent context the risk is lower because requirements.txt alone does not prove set_key is invoked, but permitting a vulnerable version still leaves the issue present in the environment.

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.